Sebastian Ruder
Person on 4 sites
Sebastian Ruder is a research scientist at Meta in Berlin, working on LLMs' multilingual abilities and on evaluation.
-
4 facts on wiqqi (opens wiqqi.app)
- Now: Research scientist at Meta, Berlin (as of November 2026) (opens wiqqi.app)
- Before: Led the multilingual team at Cohere; research scientist at Google DeepMind; research scientist at AYLIEN (opens wiqqi.app)
- PhD: NLP and deep learning, Insight Research Centre for Data Analytics (opens wiqqi.app)
-
3 channels on ppll (opens ppll.app)
-
GitHub: @sebastianruder (opens github.com)
“NLP-progress — Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.”
- Blog: ruder.io (opens www.ruder.io)
- x.com: @seb_ruder (opens x.com)
-
GitHub: @sebastianruder (opens github.com)
-
23 beliefs on korrents (opens korrents.com)
-
Reliance on public benchmark results for evaluating AI models will decrease over time. (opens korrents.com)
“The time when benchmarks lasted multiple decades has passed. Going forward, we will rely less on public benchmark results.”
-
Language models perform better on benchmark problems released before their training data cutoff, indicating data contamination inflates scores. (opens korrents.com)
“GPT models perform much better on coding problems released before their pre-training data cut-off.”
-
Retrieval-augmented generation is the most practical approach for reducing LLM hallucinations. (opens korrents.com)
“Retrieval-augmented generation (RAG; Lewis et al., 2020), which conditions on the LLM's generation on retrieved documents is the most practical paradigm IMO.”
-
Reliance on public benchmark results for evaluating AI models will decrease over time. (opens korrents.com)
-
6 recommendations on rcmnd (opens rcmnd.app)
-
Deep Learning (opens rcmnd.app)
“Read the Deep Learning book. It is available as a pdf or on Amazon .”
-
Speech and Language Processing, 2nd Edition (opens rcmnd.app)
“If you're serious about learning NLP, I would recommend to study the fundamentals first by reading Speech and Language Processing, 2nd Edition by Jurafsky and Martin .”
-
Machine Learning (Coursera) (opens rcmnd.app)
“If you're new to Machine Learning, take the Coursera Machine Learning course by Andrew Ng .”
-
Deep Learning (opens rcmnd.app)